A method, device, medium and equipment for determining target user group of a new anchor

Abstract

The present invention provides a method, device, medium and equipment for determining a target user group of a new anchor, the method comprising: determining an initial user group of a target anchor; determining a first proportion of a target user feature in the initial user group; and determining a second proportion of the target user feature in the entire site user group; determining an importance value of the target user feature based on the first proportion and the second proportion; determining a diffuse user group of the target anchor based on the importance value of the target user feature; the target user group comprises a diffuse user group and an initial user group; in this way, the initial user group of the target anchor is first determined, and then the importance value of the target user feature is determined according to the first proportion and the second proportion. Since the target user feature includes different characteristic attributes of the user, when the diffuse user group is finally accurately determined according to the importance value, the determination accuracy of the diffuse user group can be improved, and finally the target user group can be accurately determined for the new anchor, thereby improving the exposure effect of the new anchor.

Description

Technical Field

[0001] The present application relates to the field of live broadcast technology, and in particular to a method, device, medium and equipment for determining a target user group of a new anchor. Background Art

[0002] On live streaming platforms, new anchors often cannot get good exposure due to the lack of historical data. If they cannot get a certain amount of traffic in the early stage of live streaming, the new anchors will be in a state of low exposure for a long time. Even if the anchor's live streaming content is high-quality, the lack of exposure will dampen the anchor's enthusiasm and cause the loss of new anchors.

[0003] In the related art, new anchors are exposed at fixed positions, but this method still cannot accurately expose new anchors, resulting in a large amount of invalid exposure. Summary of the invention

[0004] In response to the problems existing in the prior art, the embodiments of the present invention provide a method, device, medium and equipment for determining the target user group of a new anchor, which can accurately determine the target user group for the new anchor, so as to solve or partially solve the technical problem that the prior art cannot accurately expose the new anchor, resulting in a large amount of invalid exposure of the new anchor.

[0005] A first aspect of the present invention provides a method for determining a target user group of a new anchor, the method comprising:

[0006] Determine an initial user group of a target anchor; the target anchor is any anchor among all new anchors;

[0007] For any target user feature, determining a first proportion of the target user feature in the initial user group; and determining a second proportion of the target user feature in the entire site user group;

[0008] Determine the importance value of the target user feature based on the first proportion and the second proportion;

[0009] The diffuse user group of the target anchor is determined based on the importance value of the target user feature; the target user group includes the diffuse user group and the initial user group.

[0010] In the above scheme, determining the initial user group of the target anchor includes:

[0011] Get the live broadcast zone to which the target anchor belongs;

[0012] The target anchor is exposed to users who have watched the live broadcast zone, and users who click to watch the target anchor are used as the initial user group of the target anchor.

[0013] In the above solution, determining the first proportion of the target user characteristics in the initial user group includes:

[0014] According to the formula Determine a first proportion P of the target user feature in the initial user group j ;in,

[0015] S is the initial user population, s is any initial user in the initial user population; S is the number of users in the initial user population; j is the target user feature, and the target user feature is any user feature among all user features; f s is the user feature set of user s; the I(j∈f s ) is the first indicative function. If the user feature set of the initial user s includes the target user feature j, then I(j∈f s ) takes the value of 1; if the user feature set of the initial user s does not contain the target user feature j, then I(j∈f s ) takes a value of 0.

[0016] In the above solution, determining the second proportion of the target user characteristics in the entire site user group includes:

[0017] According to the formula Determine the second proportion q of the target user characteristics in the entire site user group j ;in,

[0018] U is the entire site user group, u is any entire site user in the entire site user group, and U is the number of users in the entire site user group; j is the target user feature, and the target user feature is any user feature among all user features; f u is the user feature set of all users u on the site; the I(j∈f u ) is the second indicative function. If the user feature set of all site users u includes the target user feature j, then I(j∈f u ) takes the value of 1; if the user feature set of all site users u does not include the target user feature j, then I(j∈f u ) takes a value of 0.

[0019] In the above solution, determining the importance value of the target user feature based on the first proportion and the second proportion includes:

[0020] Based on the formula Determine the importance value a of the target user feature j ;in,

[0021] The P jis the first proportion, the q j is the second proportion, and j is the target user feature.

[0022] In the above solution, the step of determining the diffusion user group of the target anchor based on the importance value of the target user feature includes:

[0023] Based on the formula Determine the diffusion score s(c) of the current user to be diffused;

[0024] If it is determined that the diffusion score is greater than a preset diffusion threshold, the current user to be diffused is determined to be a diffusion user; the diffusion user group includes a plurality of the diffusion users; wherein,

[0025] c is the current user to be diffused, j is the target user feature, and f c is the set of all user features of user c, where a j is the importance value of the target user feature j.

[0026] A second aspect of the present invention provides a device for determining a target user group of a new anchor, the device comprising:

[0027] A first determining unit is used to determine an initial user group of a target anchor; the target anchor is any anchor among all new anchors;

[0028] The second determination unit is used to determine, for any target user feature, a first proportion of the initial target user feature in the initial user group; and determine a second proportion of the target user feature in the entire site user group; the entire site user is any user in the live broadcast platform;

[0029] A third determining unit, configured to determine an importance value of the target user feature based on the first proportion and the second proportion;

[0030] The fourth determination unit is used to determine the diffusion user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffusion user group and the initial user group.

[0031] In the above solution, the second determining unit is specifically used for:

[0032] According to the formula Determine a first proportion P of the target user feature in the initial user group j ;in,

[0033] S is the initial user population, s is any initial user in the initial user population; S is the number of users in the initial user population; j is the target user feature, and the target user feature is any user feature among all user features; f s is the user feature set of user s; the I(j∈f s ) is the first indicative function. If the user features of the initial user s include the target user features j, then I(j∈f s ) takes the value of 1; if the user features of the initial user s do not include the target user features j, then I(j∈f s ) takes a value of 0.

[0034] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0035] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods described in the first aspect are implemented.

[0036] The present invention provides a method, device, medium and equipment for determining a target user group of a new anchor, the method comprising: determining an initial user group of a target anchor; the target anchor is any anchor among all new anchors; for any target user feature, determining a first proportion of the target user feature in the initial user group; and determining a second proportion of the target user feature in the entire site user group; determining an importance value of the target user feature based on the first proportion and the second proportion; determining a diffuse user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffuse user group and the initial user group; in this way, the initial user group of the target anchor is first determined, and then the importance value of the target user feature is determined according to the first proportion and the second proportion. Since the target user feature includes different characteristic attributes of the user, when the diffuse user group is finally accurately determined according to the importance value, the determination accuracy of the diffuse user group can be improved, and finally the target user group can be accurately determined for the new anchor, thereby improving the exposure effect of the new anchor. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0038] In the attached picture:

[0039] Figure 1 A schematic diagram of a method flow for determining a new anchor's target user group according to an embodiment of the present invention is shown;

[0040] Figure 2 A schematic diagram of the structure of a device for determining a target user group for a new anchor according to an embodiment of the present invention is shown;

[0041] Figure 3 A schematic diagram showing the structure of a computer device for determining a target user group for a new anchor according to an embodiment of the present invention is shown;

[0042] Figure 4 A schematic diagram of the structure of a computer-readable storage medium for determining a target user group for a new anchor according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0043] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0044] The embodiment of the present invention provides a method for determining a target user group of a new anchor, such as Figure 1 The method comprises the following steps:

[0045] S110, determining an initial user group of a target anchor; the target anchor is any anchor among all new anchors;

[0046] When a new anchor just registers, there is no historical viewing record, which is called the cold start stage. In this embodiment, the initial user group of the target anchor needs to be determined in the cold start stage, and the target anchor is any anchor among all new anchors.

[0047] In one implementation, determining an initial user group of a target anchor includes:

[0048] Get the live broadcast zone to which the target anchor belongs;

[0049] The target anchor is exposed to users who have watched the live broadcast zone, and users who click to watch the target anchor are used as the initial user group of the target anchor.

[0050] For example, if the live broadcast zone where the target anchor is located is the game A zone, then the target anchor can be exposed to any user who has watched game A in the historical time period, and then the user who clicks and watches the target anchor will be regarded as the initial user.

[0051] In the cold start phase, when the initial users reach a certain number and form an initial user group, it enters the subsequent diffusion phase to obtain diffuse users.

[0052] In this embodiment, the number of users in the initial user group needs to be considered as follows:

[0053] If the number of initial users in the initial user group is larger, the subsequent diffusion will be more accurate, but the accumulation time will be longer. On the contrary, if the flow of the cold start phase is reduced in order to enter the diffusion phase as soon as possible, the subsequent diffusion accuracy will be reduced. Therefore, considering the above factors, the number of initial users in the initial user group in this embodiment is generally 100 to 500.

[0054] S111, for any target user feature of any initial user, determining a first proportion of the target user feature of the initial user in the initial user group; and determining a second proportion of the target user feature in the entire site user group;

[0055] In this embodiment, user characteristics may include: user attribute characteristics, user preference characteristics, etc.; the characteristic names of user attribute characteristics may include: gender, age, education level, etc.; the characteristic names of user preference characteristics may include: the live broadcast partition watched and the time period for watching the live broadcast, etc.

[0056] The feature name of each user feature has a corresponding feature value. For example, the feature values ​​of gender include male and female; the feature values ​​of age include 12-18, 19-25, 25-30, 31-35, etc. The feature values ​​of education include high school and below, undergraduate, etc.

[0057] The characteristic values ​​of the live broadcast partitions to be watched may include: game partition A, game partition B, food partition C, fitness partition D, etc.; the characteristic values ​​of the time period for watching the live broadcast may include: 22:00-24:00, 0:00-3:00, 4:00-6:00, etc.

[0058] Then the user characteristics are: a combination of feature name and feature value; for example, user characteristics may include: gender_male, age_19-25 years old, live broadcast zone_game zone A, etc.

[0059] After determining the user characteristics, this embodiment mainly uses the user characteristics for diffusion. If the user characteristics of the user to be diffused are closer to the user characteristics of the initial user group, the possibility of the user to be diffused becoming a diffused user is greater. Therefore, for any target user characteristics, determining the first proportion of the target user characteristics in the initial user group specifically includes:

[0060] According to the formula Determine the first proportion P of the target user characteristics in the initial user group j ;in,

[0061] S is the initial user population, s is any initial user in the initial user population; S is the number of users in the initial user population; j is the target user feature, which is any user feature among all user features; f s is the user feature set of user s; I(j∈f s ) is the first indicative function. If the user feature set of the initial user s contains the target user feature j, then I(j∈f s ) takes the value of 1; if the user feature set of the initial user s does not contain the target user feature j, then I(j∈f s ) takes the value of 0; that is, It means the number of initial users with target user feature j in the initial user group.

[0062] The principle of the above formula is: for the target user feature, the first indicative function is equivalent to the number of initial users with the target feature in the initial user group. The quotient obtained by dividing the number of initial users with the target feature in the initial user group by the total number of users in the initial user group is used as the first proportion of the target user feature in the initial user group.

[0063] Similarly, it is necessary to determine the second largest proportion of target user characteristics in the entire site user base, including:

[0064] According to the formula Determine the second largest proportion of the target user characteristics in the entire site user base j ;in,

[0065] U is the whole site user group, u is any whole site user in the whole site user group, and the whole site user group is the user group formed by all users on the live broadcast platform; U is the number of users in the whole site user group; j is the target user feature, f u is the user feature set of any user u in the entire site; I(j∈f u ) is the second indicative function. If the user feature set of all site users u includes the target user feature j, then I(j∈f u ) takes the value of 1; if the user feature set of all site users u does not include the target user feature j, then I(j∈f u ) takes the value of 0; that is, It means the number of users in the entire site who have target user feature j.

[0066] The principle of the above formula is: for the target user characteristics, the second indicative function is equivalent to the number of users with the target characteristics in the entire site user group. The quotient obtained by dividing the number of users with the target characteristics in the entire site user group by the total number of users in the entire site user group is used as the second proportion of the target user characteristics in the entire site user group.

[0067] In this way, the first proportion of the target user characteristics in the initial user group and the second proportion in the entire site user group are determined, laying a data foundation for the subsequent determination of the degree value of the target user characteristics.

[0068] S112, determining an importance value of the target user feature based on the first proportion and the second proportion;

[0069] In one implementation, determining the importance value of the target user feature based on the first proportion and the second proportion includes:

[0070] Based on the formula Determine the importance value a of the target user’s features j ;in,

[0071] P j is the first proportion, q j is the second proportion, and j is the target user feature.

[0072] The principle of the above formula is: the measurement of the importance value of the target feature is divided into the following parts:

[0073] p j -q j It represents the difference in the proportion of users with target feature j. The larger the difference, the greater the frequency of target feature j in the initial user group compared with the entire site user group.

[0074] It represents the ratio of the number of users with target feature j to the number of users without target feature j in the initial user group. The larger the value, the more prominent the target feature j is in the initial user group.

[0075] It represents the ratio of the number of users with target feature j to the number of users without target feature j in the entire site user population. The larger the value, the more significant the feature is in the entire site user population.

[0076] If the target feature j is more important in the initial users, then Need to be as big as possible. Need to be as small as possible, so use and The ratio of is used to measure the significant difference between the initial population and the whole population of the site, but due to The range of values ​​is very large, so taking the logarithm facilitates subsequent calculations, and finally using It can measure the proportion of the target feature j in the initial population and the overall degree of differentiation. The larger the value, the more important the target feature j is in the initial population.

[0077] The greater the importance value of the target user feature, the more obvious the target feature is in the initial user group compared to the entire site users, and the better it can represent the characteristics of the initial user group.

[0078] S113, determining a diffusion user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffusion user group and the initial user group.

[0079] In one embodiment, determining the diffusion user group of the target anchor based on the importance value of the target user feature includes:

[0080] Based on the formula Determine the diffusion score s(c) of the current user to be diffused;

[0081] If it is determined that the diffusion score is greater than the preset diffusion threshold, the current user to be diffused is determined to be a diffusion user; the diffusion user group includes multiple diffusion users; wherein,

[0082] c is the current user to be diffused, j is the target user feature, f c is the user feature set of user c, a j is the importance value of target user feature j.

[0083] In this embodiment, the users to be diffused may be active users of all site users except the initial users. Active users may be understood as users whose activity exceeds an activity threshold. The activity may be measured by the number of logins, and the activity threshold may be 1 login per day.

[0084] The principle of the above formula is: the sum of the importance values ​​of all user features of user c is taken as the diffusion score of user c. If the diffusion score is greater than the diffusion threshold, it means that user c is a diffusion user; if the diffusion score is less than the diffusion threshold, it means that user c is not a diffusion user.

[0085] The factors affecting the diffusion threshold are: if the live broadcast platform needs to diffuse more users, then the diffusion threshold is lowered; if the live broadcast platform does not need to diffuse more users, then the diffusion threshold is increased. Generally speaking, the diffusion threshold ranges from 2 to 4, preferably 3.

[0086] For example, suppose that there are 700 users with user feature F in the initial user population, and the total number of the initial user population is 1000; there are 1000 users with feature F in the entire site population, and the total number of the entire site user population is 5000; then,

[0087] The first proportion of user feature F in the initial user group is: P j =700 / 1000=0.7;

[0088] The second largest proportion of user feature F in the entire site user group is: j =1000 / 5000=0.2;

[0089] Therefore, the importance value of the target feature F is:

[0090] Assuming that in addition to target feature F, there are also target features G and target features H. In the same way as above, the importance value of target feature G is 0.5, and the importance value of target feature H is 0.9. Assuming that a user has target features F, G and H at the same time, the final diffusion score of the user is: 1.12+0.5+0.9=2.56.

[0091] If the diffusion threshold is 2, since 2.56>2, the user can be determined as a diffusion user.

[0092] In this way, the sum of the importance values ​​of all user features is used as the diffusion score of the users to be diffused, and the characteristics of different user features are fully taken into account. Then the determined diffusion score is more accurate, and the diffused user group can be accurately determined, ultimately improving the accuracy of determining the target user group of the target anchor.

[0093] Based on the same inventive concept as in the above-mentioned embodiment, this embodiment also provides a device for determining a target user group of a new anchor, such as Figure 2 As shown, the device comprises:

[0094] The first determination unit 21 is used to determine an initial user group of a target anchor; the target anchor is any anchor among all new anchors;

[0095] The second determination unit 22 is used to determine, for any target user feature, a first proportion of the initial target user feature in the initial user group; and determine a second proportion of the target user feature in the entire site user group; the entire site user is any user in the live broadcast platform;

[0096] A third determining unit 23, configured to determine an importance value of the target user feature based on the first proportion and the second proportion;

[0097] The fourth determination unit 24 is used to determine the diffusion user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffusion user group and the initial user group.

[0098] In one implementation, the second acquiring unit 22 is specifically configured to:

[0099] According to the formula Determine a first proportion P of the target user feature in the initial user groupj ;in,

[0100] S is the initial user population, s is any initial user in the initial user population; S is the number of users in the initial user population; j is the target user feature, and the target user feature is any user feature among all user features; f s is the user feature set of user s; the I(j∈f s ) is the first indicative function. If the user features of the initial user s include the target user features j, then I(j∈f s ) takes the value of 1; if the user features of the initial user s do not include the target user features j, then I(j∈f s ) takes a value of 0.

[0101] Since the device introduced in the embodiment of the present invention is a device used to implement the method for determining the target user group of a new anchor in the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, the person skilled in the art can understand the specific structure and deformation of the device, so it is not described here. All devices used in the method of the embodiment of the present invention belong to the scope of protection of the present invention.

[0102] Based on the same inventive concept, this embodiment provides a computer device 300, such as Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, any step of the method described above is implemented.

[0103] Based on the same inventive concept, this embodiment provides a computer-readable storage medium 400, such as Figure 4 As shown, a computer program 411 is stored thereon, and when the computer program 411 is executed by a processor, the steps of any of the methods described above are implemented.

[0104] Through one or more embodiments of the present invention, the present invention has the following beneficial effects or advantages:

[0105] The present invention provides a method, device, medium and equipment for determining a target user group of a new anchor, the method comprising: determining an initial user group of a target anchor; the target anchor is any anchor among all new anchors; for any target user feature, determining a first proportion of the target user feature in the initial user group; and determining a second proportion of the target user feature in the entire site user group; determining an importance value of the target user feature based on the first proportion and the second proportion; determining a diffuse user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffuse user group and the initial user group; in this way, the initial user group of the target anchor is first determined, and then the importance value of the target user feature is determined according to the first proportion and the second proportion. Since the target user feature includes different characteristic attributes of the user, when the diffuse user group is finally accurately determined according to the importance value, the determination accuracy of the diffuse user group can be improved, and finally the target user group can be accurately determined for the new anchor, thereby improving the exposure effect of the new anchor.

[0106] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0107] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0108] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0109] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0110] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0111] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in a gateway, proxy server, or system according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0112] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0113] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a target user group for a new anchor, characterized in that: The method comprises: Determine an initial user group of a target anchor; the target anchor is any anchor among all new anchors; For any target user feature, determining a first proportion of the target user feature in the initial user group; and determining a second proportion of the target user feature in the entire site user group; Determine the importance value of the target user feature based on the first proportion and the second proportion; Determine the diffusion user group of the target anchor based on the importance value of the target user feature; the target user group includes the diffusion user group and the initial user group; The determining of the importance value of the target user feature based on the first proportion and the second proportion includes: based on the formula Determine the importance value a of the target user feature j ; wherein the P j is the first proportion, the q j is the second proportion, and j is the target user feature; The determining of the diffusion user group of the target anchor based on the importance value of the target user feature includes: Based on the formula Determine the diffusion score s(c) of the current user to be diffused; If it is determined that the diffusion score is greater than a preset diffusion threshold, the current user to be diffused is determined to be a diffusion user; the diffusion user group includes a plurality of the diffusion users; wherein, c is the current user to be diffused, j is the target user feature, and f c is the set of all user features of user c, where a j is the importance value of the target user feature j.

2. The method according to claim 1, characterized in that Determine the initial user group of the target anchor, including: Get the live broadcast zone to which the target anchor belongs; The target anchor is exposed to users who have watched the live broadcast zone, and users who click to watch the target anchor are used as the initial user group of the target anchor.

3. The method according to claim 1, characterized in that The determining a first proportion of the target user feature in the initial user group includes: According to the formula Determine a first proportion P of the target user feature in the initial user group j ;in, S is the initial user population, s is any initial user in the initial user population; |S| is the number of users in the initial user population; j is the target user feature, which is any user feature among all user features; f s is the user feature set of user s; the I(j∈f s ) is the first indicative function. If the user feature set of the initial user s includes the target user feature j, then I(j∈f s ) takes the value of 1; if the user feature set of the initial user s does not contain the target user feature j, then I(j∈f s ) takes a value of 0.

4. The method according to claim 1, characterized in that Determining the second proportion of the target user characteristics in the entire site user group includes: According to the formula Determine the second proportion q of the target user characteristics in the entire site user group j ;in, U is the entire site user group, u is any site user in the entire site user group, |U| is the number of users in the entire site user group; j is the target user feature, and the target user feature is any user feature among all user features; f u is the user feature set of all users u on the site; the I(j∈f u ) is the second indicative function. If the user feature set of all site users u includes the target user feature j, then I(j∈f u ) takes the value of 1; if the user feature set of all site users u does not include the target user feature j, then I(j∈f u ) takes a value of 0.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 4 are implemented.

Images